Skip to main content

云稷识别算法库

Project description

说明

ccnet算法执行之后,每个图片输出三个文件

  • detected_pts.txt json文件,标识了识别的标点数量和位置。
  • result.tif 打上结果标点之后的,geotiff格式的原始图片。
  • result.jpg 压缩之后便于web展示的图片。

run in python env

#安装本地环境 requirements.txt CCNet_3.8.env.*,
#项目中CCNet_3.8.env.* 是linux的,可能不适用于windows、macos

conda activate CCNet #或者使用本地环境

python main.py --algorithm ccnet --model-file test/ccnet/model/mouse_hole.pth --input-path test/ccnet/images/mouse --output test/ccnet/output

python main.py --algorithm yolo --model-file test/yolo/model/sheep_counting.pt --input-path test/yolo/images --output test/yolo/output

run in docker

docker run -ti --rm -v ./test:/test --entrypoint /bin/bash harbor.hzw.ruihudata.cn/cropmirror/counting_model:v0.7

conda activate CCNet

python counting/main.py --algorithm ccnet --model-file /test/ccnet/model/mouse_hole.pth --input-path /test/ccnet/images/mouse --output /test/ccnet/output

python counting/main.py --algorithm yolo --model-file /test/yolo/model/sheep_counting.pt --input-path /test/yolo/images --output /test/yolo/output

windows 10

conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia
conda install opencv
pip install opencv-contrib-python
pip install ultralytics
pip install scipy
#https://github.com/cgohlke/geospatial-wheels/releases/tag/v2024.2.18

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cropmirror_counting-0.0.3.tar.gz (61.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

cropmirror_counting-0.0.3-py3-none-any.whl (67.9 kB view details)

Uploaded Python 3

File details

Details for the file cropmirror_counting-0.0.3.tar.gz.

File metadata

  • Download URL: cropmirror_counting-0.0.3.tar.gz
  • Upload date:
  • Size: 61.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.1.3 CPython/3.11.7 Windows/10

File hashes

Hashes for cropmirror_counting-0.0.3.tar.gz
Algorithm Hash digest
SHA256 71375268752214b860dd950b83e8ac00d2596112c2a4f81ecb7747d91bde4352
MD5 11bdeb127afb860ceaa441c7f41ea52f
BLAKE2b-256 ef94c488e1d8ac898dbed5823cb637451a85e4b14ed5f2ea7faaf2991ebd4290

See more details on using hashes here.

File details

Details for the file cropmirror_counting-0.0.3-py3-none-any.whl.

File metadata

File hashes

Hashes for cropmirror_counting-0.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 294172c17b31768dad778f47dea550f6aaadc49cfdc0b8ac0eac621b171fc5e1
MD5 4d44f7d8e690e6b799af729e910cd3d4
BLAKE2b-256 fd5973c4cf26c5e2b729b26765f0d2e563cb94c3de91d795828f45139120a582

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page